Papers by Srujana Merugu
Diverse In-Context Example Selection After Decomposing Programs and Aligned Utterances Improves Semantic Parsing (2025.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are well suited for seq2seq translation . a lack of pretraining corpora can hinder the use of LLMs for structured interpretation . |
| Approach: | They propose to decompose available ICE trees into fragments and use additional invocations to map them to corresponding utterances. |
| Outcome: | The proposed method shows visible gains on diverse parsing benchmarks on popular languages. |
Automated Digitization of Unstructured Medical Prescriptions (2023.acl-industry)
Copied to clipboard
| Challenge: | e-commerce prescription ordering is challenging in emerging markets since prescriptions are paper-based, unstructured and often, handwritten. |
| Approach: | They propose a prescription digitization system for online medicine ordering built with minimal supervision. |
| Outcome: | The proposed system achieves +5.9% gain in precision@3 and +5.6% in recall@3 over baselines on medication attribute extraction. |
RxLens: Multi-Agent LLM-powered Scan and Order for Pharmacy (2025.naacl-industry)
Copied to clipboard
| Challenge: | paper prescriptions are difficult for customers to interpret and are often unstructured, handwritten, and illegible. |
| Approach: | They propose a multi-step Large Language Model-based solution for automated pharmacy cart construction. |
| Outcome: | The proposed solution can yield up to 19% - 40% and 11% - 26% increase in Recall@3 relative to SOTA methods. |
CoMix: Guide Transformers to Code-Mix using POS structure and Phonetics (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing multilingual transformer models lack the ability to intermix words of one language into the structure of another. |
| Approach: | They propose a pretraining approach to improve representation of code-mixed data in transformer models by incorporating phonetic signals, a modified attention mechanism and weak supervision guided generation by parts-of-speech constraints. |
| Outcome: | The proposed model improves performance across four code-mixed tasks and generalizes on out-of-domain translation. |
Towards Robust Knowledge Representations in Multilingual LLMs for Equivalence and Inheritance based Consistent Reasoning (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have led to impressive linguistic capabilities and emergent reasoning behaviors. |
| Approach: | They propose to use "equivalence" and "inheritance" to evaluate LLMs' representations . they propose to combine "equal" and 'inheritory' to improve consistency across languages . |
| Outcome: | The proposed representations show that they produce conflicting answers across languages . the proposed representation improves performance across languages and improves learning and knowledge sharing. |
Intent Detection in the Age of LLMs (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Traditional approaches to intent detection struggle with out-of-scope (OOS) detection. |
| Approach: | They propose to use adaptive in-context learning and chain-of-thought prompting to detect intent in SOTA LLMs. |
| Outcome: | The proposed system achieves 2% of native accuracy with 50% less latency. |